Explaining Explainable AI

Swaroop Panda; Shatarupa Thakurta Roy

doi:10.18420/muc2020-ws111-347

Explaining Explainable AI

Swaroop Panda, Shatarupa Thakurta Roy

Research output: Contribution to journal › Conference article › peer-review

Abstract

An aspect of User friendly AI involves explanation and better transparency of AI. Explainable AI(XAI) is an emerging area of research dedicated to explain and elucidate AI systems. In order to accomplish such an explanation, XAI uses a variety of tools, devices and frameworks. However, some of these tools may prove complex or ambiguous in themselves, requiring explanation. Visualization is such a tool used extensively in XAI. In this paper, we examine how such tools can be complex and ambiguous in itself and thus distort the originally intended AI explanation. We further propose three broad ways to mitigate the risks associated with tools, devices and frameworks used in XAI systems.

Original language	English
Journal	Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)
DOIs	https://doi.org/10.18420/muc2020-ws111-347
Publication status	Published - 18 Aug 2020
Externally published	Yes
Event	Mensch und Computer 2020, MuC 2020 - Workshop on 7. Mensch-Maschine-Interaktion in sicherheitskritischen Systemen - Human and Computer 2020, MuC 2020 - Workshop on the 7th Human-Machine Interaction in Safety-Critical Systems - Magdeburg, Germany Duration: 6 Sept 2020 → 9 Sept 2020

Keywords

Explainable AI
Visualization

Access to Document

10.18420/muc2020-ws111-347

Cite this

@article{2e53b47fc14240658ffbafa95c0e887c,

title = "Explaining Explainable AI",

abstract = "An aspect of User friendly AI involves explanation and better transparency of AI. Explainable AI(XAI) is an emerging area of research dedicated to explain and elucidate AI systems. In order to accomplish such an explanation, XAI uses a variety of tools, devices and frameworks. However, some of these tools may prove complex or ambiguous in themselves, requiring explanation. Visualization is such a tool used extensively in XAI. In this paper, we examine how such tools can be complex and ambiguous in itself and thus distort the originally intended AI explanation. We further propose three broad ways to mitigate the risks associated with tools, devices and frameworks used in XAI systems.",

keywords = "Explainable AI, Visualization",

author = "Swaroop Panda and Roy, \{Shatarupa Thakurta\}",

note = "Publisher Copyright: {\textcopyright} Proceedings of the Mensch und Computer 2020 Workshop on «Workshop on User-Centered Artificial Intelligence (UCAI 2020)». Copyright held by the owner/author(s); Mensch und Computer 2020, MuC 2020 - Workshop on 7. Mensch-Maschine-Interaktion in sicherheitskritischen Systemen - Human and Computer 2020, MuC 2020 - Workshop on the 7th Human-Machine Interaction in Safety-Critical Systems ; Conference date: 06-09-2020 Through 09-09-2020",

year = "2020",

month = aug,

day = "18",

doi = "10.18420/muc2020-ws111-347",

language = "English",

journal = "Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)",

issn = "1617-5468",

publisher = "Gesellschaft fur Informatik (GI)",

}

TY - JOUR

T1 - Explaining Explainable AI

AU - Panda, Swaroop

AU - Roy, Shatarupa Thakurta

N1 - Publisher Copyright: © Proceedings of the Mensch und Computer 2020 Workshop on «Workshop on User-Centered Artificial Intelligence (UCAI 2020)». Copyright held by the owner/author(s)

PY - 2020/8/18

Y1 - 2020/8/18

N2 - An aspect of User friendly AI involves explanation and better transparency of AI. Explainable AI(XAI) is an emerging area of research dedicated to explain and elucidate AI systems. In order to accomplish such an explanation, XAI uses a variety of tools, devices and frameworks. However, some of these tools may prove complex or ambiguous in themselves, requiring explanation. Visualization is such a tool used extensively in XAI. In this paper, we examine how such tools can be complex and ambiguous in itself and thus distort the originally intended AI explanation. We further propose three broad ways to mitigate the risks associated with tools, devices and frameworks used in XAI systems.

AB - An aspect of User friendly AI involves explanation and better transparency of AI. Explainable AI(XAI) is an emerging area of research dedicated to explain and elucidate AI systems. In order to accomplish such an explanation, XAI uses a variety of tools, devices and frameworks. However, some of these tools may prove complex or ambiguous in themselves, requiring explanation. Visualization is such a tool used extensively in XAI. In this paper, we examine how such tools can be complex and ambiguous in itself and thus distort the originally intended AI explanation. We further propose three broad ways to mitigate the risks associated with tools, devices and frameworks used in XAI systems.

KW - Explainable AI

KW - Visualization

UR - https://www.scopus.com/pages/publications/85138818825

U2 - 10.18420/muc2020-ws111-347

DO - 10.18420/muc2020-ws111-347

M3 - Conference article

AN - SCOPUS:85138818825

SN - 1617-5468

JO - Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)

JF - Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)

T2 - Mensch und Computer 2020, MuC 2020 - Workshop on 7. Mensch-Maschine-Interaktion in sicherheitskritischen Systemen - Human and Computer 2020, MuC 2020 - Workshop on the 7th Human-Machine Interaction in Safety-Critical Systems

Y2 - 6 September 2020 through 9 September 2020

ER -

Explaining Explainable AI

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this